© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 119667
    Prev
    Next
    INDEX
    Explanations

    technical terms and instructions related to wiring and electrical switches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pok
    -0.07
    ulkan
    -0.07
    Defaults
    -0.07
    adel
    -0.07
    turnstile
    -0.07
    辺
    -0.07
     ReturnValue
    -0.06
    antry
    -0.06
    allas
    -0.06
    tring
    -0.06
    POSITIVE LOGITS
    roe
    0.07
    -rule
    0.06
     Gle
    0.06
     yourselves
    0.06
     den
    0.06
     rule
    0.06
     Contr
    0.06
    annes
    0.06
    emale
    0.06
     Barn
    0.06
    Activations Density 0.003%

    No Known Activations